/usr/share/pyshared/cssutils/prodparser.py is in python-cssutils 0.9.10-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 | # -*- coding: utf-8 -*-
"""Productions parser used by css and stylesheets classes to parse
test into a cssutils.util.Seq and at the same time retrieving
additional specific cssutils.util.Item objects for later use.
TODO:
- ProdsParser
- handle EOF or STOP?
- handle unknown @rules
- handle S: maybe save to Seq? parameterized?
- store['_raw']: always?
- Sequence:
- opt first(), naive impl for now
"""
__all__ = ['ProdParser', 'Sequence', 'Choice', 'Prod', 'PreDef']
__docformat__ = 'restructuredtext'
__version__ = '$Id: parse.py 1418 2008-08-09 19:27:50Z cthedot $'
from helper import pushtoken
import cssutils
import re
import string
import sys
class ParseError(Exception):
"""Base Exception class for ProdParser (used internally)."""
pass
class Done(ParseError):
"""Raised if Sequence or Choice is finished and no more Prods left."""
pass
class Exhausted(ParseError):
"""Raised if Sequence or Choice is finished but token is given."""
pass
class Missing(ParseError):
"""Raised if Sequence or Choice is not finished but no matching token given."""
pass
class NoMatch(ParseError):
"""Raised if nothing in Sequence or Choice does match."""
pass
class Choice(object):
"""A Choice of productions (Sequence or single Prod)."""
def __init__(self, *prods, **options):
"""
*prods
Prod or Sequence objects
options:
optional=False
"""
self._prods = prods
try:
self.optional = options['optional']
except KeyError, e:
for p in self._prods:
if p.optional:
self.optional = True
break
else:
self.optional = False
self.reset()
def reset(self):
"""Start Choice from zero"""
self._exhausted = False
def matches(self, token):
"""Check if token matches"""
for prod in self._prods:
if prod.matches(token):
return True
return False
def nextProd(self, token):
"""
Return:
- next matching Prod or Sequence
- ``None`` if any Prod or Sequence is optional and no token matched
- raise ParseError if nothing matches and all are mandatory
- raise Exhausted if choice already done
``token`` may be None but this occurs when no tokens left."""
if not self._exhausted:
optional = False
for x in self._prods:
if x.matches(token):
self._exhausted = True
x.reset()
return x
elif x.optional:
optional = True
else:
if not optional:
# None matched but also None is optional
raise ParseError(u'No match in %s' % self)
elif token:
raise Exhausted(u'Extra token')
def __str__(self):
return u'Choice(%s)' % u', '.join([str(x) for x in self._prods])
class Sequence(object):
"""A Sequence of productions (Choice or single Prod)."""
def __init__(self, *prods, **options):
"""
*prods
Prod or Sequence objects
**options:
minmax = lambda: (1, 1)
callback returning number of times this sequence may run
"""
self._prods = prods
try:
minmax = options['minmax']
except KeyError:
minmax = lambda: (1, 1)
self._min, self._max = minmax()
if self._max is None:
# unlimited
try:
# py2.6/3
self._max = sys.maxsize
except AttributeError:
# py<2.6
self._max = sys.maxint
self._prodcount = len(self._prods)
self.reset()
def matches(self, token):
"""Called by Choice to try to find if Sequence matches."""
for prod in self._prods:
if prod.matches(token):
return True
try:
if not prod.optional:
break
except AttributeError:
pass
return False
def reset(self):
"""Reset this Sequence if it is nested."""
self._roundstarted = False
self._i = 0
self._round = 0
def _currentName(self):
"""Return current element of Sequence, used by name"""
# TODO: current impl first only if 1st if an prod!
for prod in self._prods[self._i:]:
if not prod.optional:
return str(prod)
else:
return 'Sequence'
optional = property(lambda self: self._min == 0)
def nextProd(self, token):
"""Return
- next matching Prod or Choice
- raises ParseError if nothing matches
- raises Exhausted if sequence already done
"""
while self._round < self._max:
# for this round
i = self._i
round = self._round
p = self._prods[i]
if i == 0:
self._roundstarted = False
# for next round
self._i += 1
if self._i == self._prodcount:
self._round += 1
self._i = 0
if p.matches(token):
self._roundstarted = True
# reset nested Choice or Prod to use from start
p.reset()
return p
elif p.optional:
continue
elif round < self._min:
raise Missing(u'Missing token for production %s' % p)
elif not token:
if self._roundstarted:
raise Missing(u'Missing token for production %s' % p)
else:
raise Done()
else:
raise NoMatch(u'No matching production for token')
if token:
raise Exhausted(u'Extra token')
def __str__(self):
return u'Sequence(%s)' % u', '.join([str(x) for x in self._prods])
class Prod(object):
"""Single Prod in Sequence or Choice."""
def __init__(self, name, match, optional=False,
toSeq=None, toStore=None,
stop=False, stopAndKeep=False,
nextSor=False, mayEnd=False,
storeToken=None,
exception=None):
"""
name
name used for error reporting
match callback
function called with parameters tokentype and tokenvalue
returning True, False or raising ParseError
toSeq callback (optional) or False
calling toSeq(token, tokens) returns (type_, val) == (token[0], token[1])
to be appended to seq else simply unaltered (type_, val)
if False nothing is added
toStore (optional)
key to save util.Item to store or callback(store, util.Item)
optional = False
wether Prod is optional or not
stop = False
if True stop parsing of tokens here
stopAndKeep
if True stop parsing of tokens here but return stopping
token in unused tokens
nextSor=False
next is S or other like , or / (CSSValue)
mayEnd = False
no token must follow even defined by Sequence.
Used for operator ',/ ' currently only
storeToken = None
if True toStore saves simple token tuple and not and Item object
to store. Old style processing, TODO: resolve
exception = None
exception to be raised in case of error, normaly SyntaxErr
"""
self._name = name
self.match = match
self.optional = optional
self.stop = stop
self.stopAndKeep = stopAndKeep
self.nextSor = nextSor
self.mayEnd = mayEnd
self.storeToken = storeToken
self.exception = exception
def makeToStore(key):
"Return a function used by toStore."
def toStore(store, item):
"Set or append store item."
if key in store:
_v = store[key]
if not isinstance(_v, list):
store[key] = [_v]
store[key].append(item)
else:
store[key] = item
return toStore
if toSeq or toSeq is False:
# called: seq.append(toSeq(value))
self.toSeq = toSeq
else:
self.toSeq = lambda t, tokens: (t[0], t[1])
if hasattr(toStore, '__call__'):
self.toStore = toStore
elif toStore:
self.toStore = makeToStore(toStore)
else:
# always set!
self.toStore = None
def matches(self, token):
"""Return if token matches."""
if not token:
return False
type_, val, line, col = token
return self.match(type_, val)
def reset(self):
pass
def __str__(self):
return self._name
def __repr__(self):
return "<cssutils.prodsparser.%s object name=%r at 0x%x>" % (
self.__class__.__name__, self._name, id(self))
# global tokenizer as there is only one!
tokenizer = cssutils.tokenize2.Tokenizer()
class ProdParser(object):
"""Productions parser."""
def __init__(self, clear=True):
self.types = cssutils.cssproductions.CSSProductions
self._log = cssutils.log
if clear:
tokenizer.clear()
def _texttotokens(self, text):
"""Build a generator which is the only thing that is parsed!
old classes may use lists etc
"""
if isinstance(text, basestring):
# DEFAULT, to tokenize strip space
return tokenizer.tokenize(text.strip())
elif isinstance(text, tuple):
# OLD: (token, tokens) or a single token
if len(text) == 2:
# (token, tokens)
chain([token], tokens)
else:
# single token
return iter([text])
elif isinstance(text, list):
# OLD: generator from list
return iter(text)
else:
# DEFAULT, already tokenized, assume generator
return text
def _SorTokens(self, tokens, until=',/'):
"""New tokens generator which has S tokens removed,
if followed by anything in ``until``, normally a ``,``."""
for token in tokens:
if token[0] == self.types.S:
try:
next_ = tokens.next()
except StopIteration:
yield token
else:
if next_[1] in until:
# omit S as e.g. ``,`` has been found
yield next_
elif next_[0] == self.types.COMMENT:
# pass COMMENT
yield next_
else:
yield token
yield next_
elif token[0] == self.types.COMMENT:
# pass COMMENT
yield token
else:
yield token
break
# normal mode again
for token in tokens:
yield token
def parse(self, text, name, productions, keepS=False, store=None):
"""
text (or token generator)
to parse, will be tokenized if not a generator yet
may be:
- a string to be tokenized
- a single token, a tuple
- a tuple of (token, tokensGenerator)
- already tokenized so a tokens generator
name
used for logging
productions
used to parse tokens
keepS
if WS should be added to Seq or just be ignored
store UPDATED
If a Prod defines ``toStore`` the key defined there
is a key in store to be set or if store[key] is a list
the next Item is appended here.
TODO: NEEDED? :
Key ``raw`` is always added and holds all unprocessed
values found
returns
:wellformed: True or False
:seq: a filled cssutils.util.Seq object which is NOT readonly yet
:store: filled keys defined by Prod.toStore
:unusedtokens: token generator containing tokens not used yet
"""
tokens = self._texttotokens(text)
if not tokens:
self._log.error(u'No content to parse.')
# TODO: return???
seq = cssutils.util.Seq(readonly=False)
if not store: # store for specific values
store = {}
prods = [productions] # stack of productions
wellformed = True
# while no real token is found any S are ignored
started = False
stopall = False
prod = None
# flag if default S handling should be done
defaultS = True
while True:
try:
token = tokens.next()
except StopIteration:
break
type_, val, line, col = token
# default productions
if type_ == self.types.COMMENT:
# always append COMMENT
seq.append(cssutils.css.CSSComment(val),
cssutils.css.CSSComment, line, col)
elif defaultS and type_ == self.types.S:
# append S (but ignore starting ones)
if not keepS or not started:
continue
else:
seq.append(val, type_, line, col)
# elif type_ == self.types.ATKEYWORD:
# # @rule
# r = cssutils.css.CSSUnknownRule(cssText=val)
# seq.append(r, type(r), line, col)
elif type_ == self.types.INVALID:
# invalidate parse
wellformed = False
self._log.error(u'Invalid token: %r' % (token,))
break
elif type_ == 'EOF':
# do nothing? (self.types.EOF == True!)
pass
else:
started = True # check S now
nextSor = False # reset
try:
while True:
# find next matching production
try:
prod = prods[-1].nextProd(token)
except (Exhausted, NoMatch), e:
# try next
prod = None
if isinstance(prod, Prod):
# found actual Prod, not a Choice or Sequence
break
elif prod:
# nested Sequence, Choice
prods.append(prod)
else:
# nested exhausted, try in parent
if len(prods) > 1:
prods.pop()
else:
raise ParseError('No match')
except ParseError, e:
wellformed = False
self._log.error(u'%s: %s: %r' % (name, e, token))
break
else:
# process prod
if prod.toSeq and not prod.stopAndKeep:
type_, val = prod.toSeq(token, tokens)
if val is not None:
seq.append(val, type_, line, col)
if prod.toStore:
if not prod.storeToken:
prod.toStore(store, seq[-1])
else:
# workaround for now for old style token
# parsing!
# TODO: remove when all new style
prod.toStore(store, token)
if prod.stop: # EOF?
# stop here and ignore following tokens
break
if prod.stopAndKeep: # e.g. ;
# stop here and ignore following tokens
# but keep this token for next run
tokenizer.push(token)
stopall = True
break
if prod.nextSor:
# following is S or other token (e.g. ",")?
# remove S if
tokens = self._SorTokens(tokens, ',/')
defaultS = False
else:
defaultS = True
lastprod = prod
if not stopall:
# stop immediately
while True:
# all productions exhausted?
try:
prod = prods[-1].nextProd(token=None)
except Done, e:
# ok
prod = None
except Missing, e:
prod = None
# last was a S operator which may End a Sequence, then ok
if hasattr(lastprod, 'mayEnd') and not lastprod.mayEnd:
wellformed = False
self._log.error(u'%s: %s' % (name, e))
except ParseError, e:
prod = None
wellformed = False
self._log.error(u'%s: %s' % (name, e))
else:
if prods[-1].optional:
prod = None
elif prod and prod.optional:
# ignore optional
continue
if prod and not prod.optional:
wellformed = False
self._log.error(u'%s: Missing token for production %r'
% (name, str(prod)))
break
elif len(prods) > 1:
# nested exhausted, next in parent
prods.pop()
else:
break
# trim S from end
seq.rstrip()
return wellformed, seq, store, tokens
class PreDef(object):
"""Predefined Prod definition for use in productions definition
for ProdParser instances.
"""
types = cssutils.cssproductions.CSSProductions
reHexcolor = re.compile(r'^\#(?:[0-9abcdefABCDEF]{3}|[0-9abcdefABCDEF]{6})$')
@staticmethod
def calc(toSeq=None, nextSor=False):
return Prod(name=u'calcfunction',
match=lambda t, v: u'calc(' == cssutils.helper.normalize(v),
toSeq=toSeq,
nextSor=nextSor)
@staticmethod
def char(name='char', char=u',', toSeq=None,
stop=False, stopAndKeep=False,
optional=True, nextSor=False):
"any CHAR"
return Prod(name=name, match=lambda t, v: v == char, toSeq=toSeq,
stop=stop, stopAndKeep=stopAndKeep, optional=optional,
nextSor=nextSor)
@staticmethod
def comma():
return PreDef.char(u'comma', u',')
@staticmethod
def dimension(nextSor=False, stop=False):
return Prod(name=u'dimension',
match=lambda t, v: t == PreDef.types.DIMENSION,
toSeq=lambda t, tokens: (t[0], cssutils.helper.normalize(t[1])),
stop=stop,
nextSor=nextSor)
@staticmethod
def function(toSeq=None, nextSor=False):
return Prod(name=u'function',
match=lambda t, v: t == PreDef.types.FUNCTION,
toSeq=toSeq,
nextSor=nextSor)
@staticmethod
def funcEnd(stop=False):
")"
return PreDef.char(u'end FUNC ")"', u')',
stop=stop)
@staticmethod
def hexcolor(stop=False, nextSor=False):
"#123 or #123456"
return Prod(name='HEX color',
match=lambda t, v: (
t == PreDef.types.HASH and
PreDef.reHexcolor.match(v)
),
stop=stop,
nextSor=nextSor)
@staticmethod
def ident(stop=False, toStore=None, nextSor=False):
return Prod(name=u'ident',
match=lambda t, v: t == PreDef.types.IDENT,
stop=stop,
toStore=toStore,
nextSor=nextSor)
@staticmethod
def number(stop=False, toSeq=None, nextSor=False):
return Prod(name=u'number',
match=lambda t, v: t == PreDef.types.NUMBER,
stop=stop,
toSeq=toSeq,
nextSor=nextSor)
@staticmethod
def percentage(stop=False, toSeq=None, nextSor=False):
return Prod(name=u'percentage',
match=lambda t, v: t == PreDef.types.PERCENTAGE,
stop=stop,
toSeq=toSeq,
nextSor=nextSor)
@staticmethod
def string(stop=False, nextSor=False):
"string delimiters are removed by default"
return Prod(name=u'string',
match=lambda t, v: t == PreDef.types.STRING,
toSeq=lambda t, tokens: (t[0], cssutils.helper.stringvalue(t[1])),
stop=stop,
nextSor=nextSor)
@staticmethod
def S(name=u'whitespace', toSeq=None, optional=False):
return Prod(name=name,
match=lambda t, v: t == PreDef.types.S,
toSeq=toSeq,
optional=optional,
mayEnd=True)
@staticmethod
def unary(stop=False, toSeq=None, nextSor=False):
"+ or -"
return Prod(name=u'unary +-', match=lambda t, v: v in (u'+', u'-'),
optional=True,
stop=stop,
toSeq=toSeq,
nextSor=nextSor)
@staticmethod
def uri(stop=False, nextSor=False):
"'url(' and ')' are removed and URI is stripped"
return Prod(name=u'URI',
match=lambda t, v: t == PreDef.types.URI,
toSeq=lambda t, tokens: (t[0], cssutils.helper.urivalue(t[1])),
stop=stop,
nextSor=nextSor)
@staticmethod
def unicode_range(stop=False, nextSor=False):
"u+123456-abc normalized to lower `u`"
return Prod(name='unicode-range',
match=lambda t, v: t == PreDef.types.UNICODE_RANGE,
toSeq=lambda t, tokens: (t[0], t[1].lower()),
stop=stop,
nextSor=nextSor
)
@staticmethod
def variable(toSeq=None, stop=False, nextSor=False):
return Prod(name=u'variable',
match=lambda t, v: u'var(' == cssutils.helper.normalize(v),
toSeq=toSeq,
stop=stop,
nextSor=nextSor)
# used for MarginRule for now:
@staticmethod
def unknownrule(name=u'@', toStore=None):
"""@rule dummy (matches ATKEYWORD to remove unknown rule tokens from
stream::
@x;
@x {...}
no nested yet!
"""
def rule(tokens):
saved = []
for t in tokens:
saved.append(t)
if (t[1] == u'}' or t[1] == u';'):
return cssutils.css.CSSUnknownRule(saved)
return Prod(name=name,
match=lambda t, v: t == u'ATKEYWORD',
toSeq=lambda t, tokens: (u'CSSUnknownRule',
rule(pushtoken(t, tokens))
),
toStore=toStore
)
|